Content & Media

Use when creating, improving, or troubleshooting Claude Code subagents. Expert guidance on agent design, system prompts, tool access, model selection, and best practices for building specialized AI assistants.

Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.

Write focused tests for core user flows and critical paths with clear test names, behavior-focused assertions, mocked external dependencies, and fast execution, deferring edge case testing until explicitly required. Use this skill when creating or modifying test files, writing unit tests, integration tests, or test cases for any feature. Apply when writing test files (test/, __tests__/, spec/, .test.js, .spec.ts, test_*.py), implementing tests for core user workflows, testing critical business logic, mocking external dependencies (databases, APIs, file systems), writing descriptive test names, creating fast-running unit tests, or adding tests at logical completion points of feature development. Use for any task involving test creation, test coverage, test strategy, or test-driven development.

Expert guidance for creating Claude Code slash commands with correct frontmatter, structure, and best practices

Use when creating, improving, or troubleshooting Claude Code slash commands. Expert guidance on command structure, arguments, frontmatter, tool permissions, and best practices for building effective custom commands.

Step-by-step guide for adding support for a new AI editor format to PRPM - covers types, converters, schemas, CLI, webapp, and testing

Comprehensive guide to troubleshooting Pulumi TypeScript errors, infrastructure issues, and best practices - covers common errors, Outputs handling, AWS Beanstalk deployment, and cost optimization

Use when creating agents.md files - provides plain markdown format with NO frontmatter, free-form structure, and project context guidelines for AI coding assistants

Systematically review completed code implementations against original plans, requirements, and coding standards to ensure quality, plan alignment, and best practices adherence. Use this skill after completing any significant implementation work including features, refactorings, bug fixes, or architectural changes, when a numbered step or phase from a planning document has been finished, after implementing multiple related functions or components that form a logical unit, when finishing work that was specified in a technical specification or design document, after making substantial changes to existing code or architecture, before creating pull requests to validate implementation quality, when completing API endpoints, service layers, or data access implementations, after implementing test suites for new functionality, when refactoring code to ensure no behavior was inadvertently changed, after integrating with external systems or third-party services, when finishing user-facing features to verify requirements

Use when creating Continue rules - provides required name field, alwaysApply semantics, glob/regex patterns, and markdown format with optional frontmatter

Expert guidance for developing Claude Code hooks in TypeScript with shared utilities, esbuild compilation, and Vitest testing - distributes compiled JS while maintaining TypeScript development experience

Apply rigorous test-driven development methodology following the Red-Green-Refactor cycle (write failing test, implement minimal code to pass, refactor while staying green) that ensures tests genuinely verify behavior by requiring observed failure before implementation, preventing untested code and false-positive tests. Use this skill when implementing any new feature or functionality in any programming language, when fixing bugs or resolving defects in existing code, when refactoring code to improve design while preserving behavior, when adding new methods, functions, classes, or modules to a codebase, when modifying existing behavior or business logic, when writing code in any file that will be executed in production environments, when creating API endpoints, service methods, or controller actions, when implementing data validation, transformation, or processing logic, when building user interface components with testable behavior, when writing algorithms, calculations, or business rules, when integrating w

Generate presentation slides from images or PDF files. Use when user wants to create slides, generate presentations, or convert PDF to slides for the training camp website. Triggers on keywords like "slides", "presentation", "幻灯片", "演示文稿".

Use when you need to create a new custom skill for a profile - guides through gathering requirements, creating directory structure, writing SKILL.md, and optionally adding bundled scripts

Use this skill to build features or debug anything that uses a webapp frontend.

Use when implementing user interfaces or user experiences - guides through exploration of design variations, frontend setup, iteration, and proper integration

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Connects Figma design components to code components using Code Connect. Use when user says "code connect", "connect this component to code", "connect Figma to code", "map this component", "link component to code", "create code connect mapping", "add code connect", "connect design to code", or wants to establish mappings between Figma designs and code implementations. Requires Figma MCP server connection.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first